BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluation
This addresses the challenge of automated hypothesis generation for researchers, offering a flexible and practical tool, though it appears incremental as it builds on existing agentic architectures with enhancements.
The paper tackles the problem of generating novel and evidence-grounded hypotheses in scientific research by proposing BioDisco, a multi-agent framework that integrates language models, dual-mode evidence, and iterative feedback, resulting in superior novelty and significance over existing methods as demonstrated through evaluations.
Identifying novel hypotheses is essential to scientific research, yet this process risks being overwhelmed by the sheer volume and complexity of available information. Existing automated methods often struggle to generate novel and evidence-grounded hypotheses, lack robust iterative refinement and rarely undergo rigorous temporal evaluation for future discovery potential. To address this, we propose BioDisco, a multi-agent framework that draws upon language model-based reasoning and a dual-mode evidence system (biomedical knowledge graphs and automated literature retrieval) for grounded novelty, integrates an internal scoring and feedback loop for iterative refinement, and validates performance through pioneering temporal and human evaluations and a Bradley-Terry paired comparison model to provide statistically-grounded assessment. Our evaluations demonstrate superior novelty and significance over ablated configurations representative of existing agentic architectures. Designed for flexibility and modularity, BioDisco allows seamless integration of custom language models or knowledge graphs, and can be run with just a few lines of code. We anticipate researchers using this practical tool as a catalyst for the discovery of new hypotheses.